
# for data manipulation and analysis
import numpy as np
import pandas as pd
import pyspark
from pyspark.sql import SparkSession

# for visualisation
import seaborn as sns
import plotly.express as px
import plotly.subplots as sp
import plotly.graph_objects as go
from plotly.subplots import make_subplots
import matplotlib.pyplot as plt


df = pd.read_csv('/Users/suryanshjamwal/Desktop/Analytics Case studies/Spotify/Spotify_Youtube.csv')

df


df.head()


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 20718 entries, 0 to 20717
Data columns (total 28 columns):
 #   Column            Non-Null Count  Dtype  
---  ------            --------------  -----  
 0   Unnamed: 0        20718 non-null  int64  
 1   Artist            20718 non-null  object 
 2   Url_spotify       20718 non-null  object 
 3   Track             20718 non-null  object 
 4   Album             20718 non-null  object 
 5   Album_type        20718 non-null  object 
 6   Uri               20718 non-null  object 
 7   Danceability      20716 non-null  float64
 8   Energy            20716 non-null  float64
 9   Key               20716 non-null  float64
 10  Loudness          20716 non-null  float64
 11  Speechiness       20716 non-null  float64
 12  Acousticness      20716 non-null  float64
 13  Instrumentalness  20716 non-null  float64
 14  Liveness          20716 non-null  float64
 15  Valence           20716 non-null  float64
 16  Tempo             20716 non-null  float64
 17  Duration_ms       20716 non-null  float64
 18  Url_youtube       20248 non-null  object 
 19  Title             20248 non-null  object 
 20  Channel           20248 non-null  object 
 21  Views             20248 non-null  float64
 22  Likes             20177 non-null  float64
 23  Comments          20149 non-null  float64
 24  Description       19842 non-null  object 
 25  Licensed          20248 non-null  object 
 26  official_video    20248 non-null  object 
 27  Stream            20142 non-null  float64
dtypes: float64(15), int64(1), object(12)
memory usage: 4.4+ MB


df = df.drop(['Unnamed: 0', 'Title', 'Url_spotify', 'Uri', 'Description', 'official_video', 'Channel', 'Url_youtube'], axis = 1)


df.columns

Index(['Artist', 'Track', 'Album', 'Album_type', 'Danceability', 'Energy',
       'Key', 'Loudness', 'Speechiness', 'Acousticness', 'Instrumentalness',
       'Liveness', 'Valence', 'Tempo', 'Duration_ms', 'Views', 'Likes',
       'Comments', 'Licensed', 'Stream'],
      dtype='object')


df = df.dropna()


df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 19549 entries, 0 to 20717
Data columns (total 20 columns):
 #   Column            Non-Null Count  Dtype  
---  ------            --------------  -----  
 0   Artist            19549 non-null  object 
 1   Track             19549 non-null  object 
 2   Album             19549 non-null  object 
 3   Album_type        19549 non-null  object 
 4   Danceability      19549 non-null  float64
 5   Energy            19549 non-null  float64
 6   Key               19549 non-null  float64
 7   Loudness          19549 non-null  float64
 8   Speechiness       19549 non-null  float64
 9   Acousticness      19549 non-null  float64
 10  Instrumentalness  19549 non-null  float64
 11  Liveness          19549 non-null  float64
 12  Valence           19549 non-null  float64
 13  Tempo             19549 non-null  float64
 14  Duration_ms       19549 non-null  float64
 15  Views             19549 non-null  float64
 16  Likes             19549 non-null  float64
 17  Comments          19549 non-null  float64
 18  Licensed          19549 non-null  object 
 19  Stream            19549 non-null  float64
dtypes: float64(15), object(5)
memory usage: 3.1+ MB


df.describe()


df = df.drop_duplicates(['Track'])

df


numeric_df = df.select_dtypes(include=np.number)


numeric_df


numeric_df.describe()


plt.figure(figsize=(16, 10))
heatmap = sns.heatmap(numeric_df.corr(), vmin=-1, vmax=1, annot=True, cmap='BrBG')
heatmap.set_title('Correlation Heatmap', fontdict={'fontsize':19}, pad=12);
plt.savefig('heatmap.png', dpi=550, bbox_inches='tight')


# Using spark.sql to query dataframe

spark = SparkSession.builder.appName(
  "pyspark.sql").getOrCreate()

df_spark = spark.createDataFrame(df)
 
df_spark.show()

Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).
23/05/02 18:28:33 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
[Stage 0:>                                                          (0 + 1) / 1]

+--------------------+--------------------+--------------------+----------+------------+------+----+--------+-----------+------------+----------------+--------+-------+-------+-----------+-------------+---------+--------+--------+-------------+
|              Artist|               Track|               Album|Album_type|Danceability|Energy| Key|Loudness|Speechiness|Acousticness|Instrumentalness|Liveness|Valence|  Tempo|Duration_ms|        Views|    Likes|Comments|Licensed|       Stream|
+--------------------+--------------------+--------------------+----------+------------+------+----+--------+-----------+------------+----------------+--------+-------+-------+-----------+-------------+---------+--------+--------+-------------+
|            Gorillaz|      Feel Good Inc.|          Demon Days|     album|       0.818| 0.705| 6.0|  -6.679|      0.177|     0.00836|         0.00233|   0.613|  0.772|138.559|   222640.0| 6.93555221E8|6220896.0|169907.0|    true|1.040234854E9|
|            Gorillaz|     Rhinestone Eyes|       Plastic Beach|     album|       0.676| 0.703| 8.0|  -5.815|     0.0302|      0.0869|         6.87E-4|  0.0463|  0.852| 92.761|   200173.0|  7.2011645E7|1079128.0| 31003.0|    true| 3.10083733E8|
|            Gorillaz|New Gold (feat. T...|New Gold (feat. T...|    single|       0.695| 0.923| 1.0|   -3.93|     0.0522|      0.0425|          0.0469|   0.116|  0.551|108.014|   215150.0|    8435055.0| 282142.0|  7399.0|    true|  6.3063467E7|
|            Gorillaz|  On Melancholy Hill|       Plastic Beach|     album|       0.689| 0.739| 2.0|   -5.81|      0.026|     1.51E-5|           0.509|   0.064|  0.578|120.423|   233867.0| 2.11754952E8|1788577.0| 55229.0|    true| 4.34663559E8|
|            Gorillaz|      Clint Eastwood|            Gorillaz|     album|       0.663| 0.694|10.0|  -8.627|      0.171|      0.0253|             0.0|  0.0698|  0.525|167.953|   340920.0| 6.18480958E8|6197318.0|155930.0|    true| 6.17259738E8|
|            Gorillaz|                DARE|          Demon Days|     album|        0.76| 0.891|11.0|  -5.852|     0.0372|      0.0229|          0.0869|   0.298|  0.966|120.264|   245000.0| 2.59021161E8|1844658.0| 72008.0|    true| 3.23850327E8|
|            Gorillaz|New Gold (feat. T...|New Gold (feat. T...|    single|       0.716| 0.897| 4.0|  -7.185|     0.0629|       0.012|           0.262|   0.325|  0.358| 127.03|   274142.0|     451996.0|  11686.0|   241.0|   false|  1.0666154E7|
|            Gorillaz|She's My Collar (...|     Humanz (Deluxe)|     album|       0.726| 0.815|11.0|  -5.886|     0.0313|     0.00799|           0.081|   0.112|  0.462|140.158|   209560.0|    1010982.0|  17675.0|   260.0|   false| 1.59605929E8|
|            Gorillaz|Cracker Island (f...|Cracker Island (f...|    single|       0.741| 0.913| 2.0|   -3.34|     0.0465|     0.00343|           0.103|   0.325|  0.643|120.012|   213750.0|   2.445982E7| 739527.0| 20296.0|    true|  4.2671901E7|
|            Gorillaz|         Dirty Harry|          Demon Days|     album|       0.625| 0.877|10.0|  -7.176|      0.162|      0.0315|          0.0811|   0.672|  0.865|192.296|   230426.0| 1.54761056E8|1386920.0| 39240.0|    true| 1.91074713E8|
|Red Hot Chili Pep...|     Californication|Californication (...|     album|       0.592| 0.767| 9.0|  -2.788|      0.027|      0.0021|         0.00165|   0.127|  0.328| 96.483|   329733.0|1.018811259E9|4394471.0|121452.0|    true|1.055738398E9|
|Red Hot Chili Pep...|    Under the Bridge|Blood Sugar Sex M...|     album|       0.559| 0.345| 4.0| -13.496|     0.0459|      0.0576|         1.05E-4|   0.141|  0.458| 84.581|   264307.0| 2.46687714E8|1213572.0| 32761.0|    true|1.061750522E9|
|Red Hot Chili Pep...|          Can't Stop|By the Way (Delux...|     album|       0.618| 0.938| 9.0|  -3.442|     0.0456|      0.0179|             0.0|   0.167|  0.875| 91.455|   269000.0| 3.36635759E8|1740224.0| 32573.0|    true| 8.66464951E8|
|Red Hot Chili Pep...|         Scar Tissue|Californication (...|     album|       0.595| 0.717| 0.0|  -4.803|     0.0295|      0.0779|         0.00274|   0.108|  0.547| 88.969|   215907.0|  4.3512153E8|1890900.0| 37069.0|    true| 6.13838674E8|
|Red Hot Chili Pep...|           Otherside|Californication (...|     album|       0.458| 0.795| 0.0|  -3.265|     0.0574|     0.00316|         2.02E-4|  0.0756|  0.513|123.229|   255373.0| 6.73528656E8|3140356.0| 60091.0|    true| 7.32774515E8|
|Red Hot Chili Pep...|       Snow (Hey Oh)|    Stadium Arcadium|     album|       0.427|   0.9|11.0|  -3.674|     0.0499|       0.116|         1.75E-5|   0.119|  0.599|104.655|   334667.0| 3.20871237E8|1272266.0| 37004.0|    true| 8.60722316E8|
|Red Hot Chili Pep...|     Dani California|    Stadium Arcadium|     album|       0.556| 0.913| 0.0|   -2.36|     0.0437|      0.0193|         8.59E-6|   0.346|   0.73| 96.184|   282160.0| 3.24228662E8|1456622.0| 49461.0|    true| 5.50067391E8|
|Red Hot Chili Pep...|          By the Way|By the Way (Delux...|     album|       0.451|  0.97| 0.0|  -4.938|      0.107|      0.0264|         0.00355|   0.102|  0.198|122.444|   216933.0| 1.79005296E8| 784717.0| 20084.0|    true| 3.67485508E8|
|Red Hot Chili Pep...|        Give It Away|Blood Sugar Sex M...|     album|       0.666| 0.936| 7.0|  -9.919|     0.0476|     0.00244|           0.086|   0.153|  0.776| 91.577|   282907.0|  8.6637926E7| 434837.0| 16029.0|    true| 3.01947159E8|
|Red Hot Chili Pep...|    Dark Necessities|         The Getaway|     album|         0.7| 0.742| 5.0|  -6.777|     0.0716|      0.0722|          0.0199|    0.11|  0.197| 91.959|   302000.0| 4.40037964E8|2094182.0| 56516.0|    true| 3.85677873E8|
+--------------------+--------------------+--------------------+----------+------------+------+----+--------+-----------+------------+----------------+--------+-------+-------+-----------+-------------+---------+--------+--------+-------------+
only showing top 20 rows


# Saving the top 600 tracks for later

df_spark.createOrReplaceTempView("table0")

df600_spot = spark.sql('''
SELECT *
FROM table0 
ORDER BY Stream DESC
LIMIT 600''').toPandas()

df600_spot


df600_YT = spark.sql('''
SELECT *
FROM table0 
ORDER BY Views DESC
LIMIT 600''').toPandas()

df600_YT


df_spark.createOrReplaceTempView("table1")

sqlDF = spark.sql('''
SELECT Album_type, 
ROUND((COUNT(Album_type)*1.0/(SELECT COUNT(Album_type) FROM table1)*100),2) AS perc 
FROM table1 
GROUP BY Album_type''').toPandas()

irises_colors = ['rgb(33, 75, 99)', 'rgb(79, 129, 102)', 'rgb(151, 179, 100)']
fig = go.Figure(data=[go.Pie(labels=sqlDF['Album_type'], values=sqlDF['perc'], hole=.5, pull=[0.02, 0.02, 0.02], marker_colors=irises_colors)])
fig.show()


df_spark.createOrReplaceTempView("table2")

sqlDF = spark.sql('''SELECT Artist, 
AVG(Danceability) AS Danceability, AVG(Energy) AS Energy, AVG(Key) AS Key, 
AVG(Loudness) AS Loudness, AVG(Speechiness) AS Speechiness, 
AVG(Acousticness) AS Acousticness, AVG(Instrumentalness) AS Instrumentalness, AVG(Liveness) AS Liveness,
AVG(Valence) AS Valence, AVG(Tempo) AS Tempo, AVG(Duration_ms) AS Duration_ms,
AVG(Views) AS Views, AVG(Likes) AS Likes, AVG(Comments) AS Comments, AVG(Stream) AS Stream
FROM table2 
GROUP BY Artist 
ORDER BY Views DESC 
LIMIT 10;''').toPandas()

sqlDF

23/05/02 18:28:46 WARN package: Truncated the string representation of a plan since it was too large. This behavior can be adjusted by setting 'spark.sql.debug.maxToStringFields'.


metrics = ['Views', 'Likes', 'Comments', 'Stream', 'Danceability', 'Energy', 'Key', 'Loudness', 'Speechiness', 'Acousticness', 'Instrumentalness', 'Liveness', 'Valence','Tempo', 'Duration_ms']

num_metrics = len(metrics)
cols = 2
rows = (num_metrics + cols - 1) // cols

fig = sp.make_subplots(rows=rows, cols=cols, subplot_titles=metrics, vertical_spacing=0.03, horizontal_spacing=0.035)

for i, metric in enumerate(metrics):
    row = i // cols + 1
    col = i % cols + 1
    trace = go.Bar(x=sqlDF[sqlDF.columns[0]], y=sqlDF[metric], name=metric,
                   text=sqlDF[metric], textposition='outside', texttemplate='%{text:.2f}',
                   textfont=dict(size=8))
    fig.add_trace(trace, row=row, col=col)

fig.update_layout( title_text='Average Metrics by Top Artists', title_x=0.5, font=dict(size=9),
                  height=400 * rows, width=500 * cols, showlegend=False)

for i in fig['layout']['annotations']:
    i['font'] = dict(size=14)

fig.show()


df_spark.createOrReplaceTempView("table3")

sqlDF = spark.sql('''SELECT Artist, 
AVG(Danceability) AS Danceability, AVG(Energy) AS Energy, AVG(Key) AS Key, 
AVG(Loudness) AS Loudness, AVG(Speechiness) AS Speechiness, 
AVG(Acousticness) AS Acousticness, AVG(Instrumentalness) AS Instrumentalness, AVG(Liveness) AS Liveness,
AVG(Valence) AS Valence, AVG(Tempo) AS Tempo, AVG(Duration_ms) AS Duration_ms,
AVG(Views) AS Views, AVG(Likes) AS Likes, AVG(Comments) AS Comments, AVG(Stream) AS Stream
FROM table3
GROUP BY Artist 
ORDER BY Stream DESC 
LIMIT 10;''').toPandas()

sqlDF


metrics = ['Stream', 'Views', 'Likes', 'Comments', 'Danceability', 'Energy', 'Key', 'Loudness', 'Speechiness', 'Acousticness', 'Instrumentalness', 'Liveness', 'Valence','Tempo', 'Duration_ms']

fig = sp.make_subplots(rows=rows, cols=cols, subplot_titles=metrics, vertical_spacing=0.03, horizontal_spacing=0.035)

for i, metric in enumerate(metrics):
    row = i // cols + 1
    col = i % cols + 1
    trace = go.Bar(x=sqlDF[sqlDF.columns[0]], y=sqlDF[metric], name=metric,
                   text=sqlDF[metric], textposition='outside', texttemplate='%{text:.2f}',
                   textfont=dict(size=8))
    fig.add_trace(trace, row=row, col=col)

fig.update_layout( title_text='Average Metrics by Top Artists', title_x=0.5, font=dict(size=9),
                  height=400 * rows, width=500 * cols, showlegend=False)

for i in fig['layout']['annotations']:
    i['font'] = dict(size=14)

fig.show()


df_spark.createOrReplaceTempView("table4")

sqlDF = spark.sql('''SELECT *
FROM table4
ORDER BY Views DESC 
LIMIT 10;''').toPandas()

sqlDF


df_spark.createOrReplaceTempView("table5")

sqlDF = spark.sql('''SELECT *
FROM table5
ORDER BY Stream DESC 
LIMIT 10;''').toPandas()

sqlDF


fig = px.scatter(df, x=df['Danceability'], y=df['Views'], color=df['Energy'], hover_data=['Track'])
fig.show()


fig = px.scatter(df, x=df['Speechiness'], y=df['Views'], color = df['Energy'], hover_data=['Track'])
fig.show()


fig = px.scatter(df, x=df['Tempo'], y=df['Views'], hover_data=['Track'])
fig.show()


fig = px.scatter(df, x=df['Valence'], y=df['Stream'], color=df['Energy'], hover_data=['Track'])
fig.show()


fig = px.scatter(df, x=df['Danceability'], y=df['Tempo'],
                 color=df['Stream'], trendline = 'ols')
fig.show()


fig = px.scatter(df, x=df['Loudness'], y=df['Views'], color=df['Danceability'], hover_data=['Track'])
fig.show()


df['V/L_Ratio'] = df['Likes']/ df['Views']
df['V/L_Ratio'] = df['V/L_Ratio'].apply(lambda x: round(x, 4))
vl = df.sort_values(by = 'V/L_Ratio', ascending = False).head(20)[['Track', 'Artist', 'Views', 'Likes', 'V/L_Ratio']]

fig = px.bar(vl, x=vl['Track'], y=vl['V/L_Ratio'],
             hover_data=['Artist'])
fig.show()


df_spark.createOrReplaceTempView("table6")

sqlDF = spark.sql('''SELECT Album, Artist, SUM(Stream) AS Streams
FROM table6
GROUP BY Album, Artist
ORDER BY SUM(Stream) DESC 
LIMIT 15;''').toPandas()

sqlDF

fig = px.line(sqlDF, x=sqlDF['Album'], y=sqlDF['Streams'],
             hover_data=['Artist'], markers=True)
fig.show()


df_spark.createOrReplaceTempView("table7")

sqlDF = spark.sql('''SELECT Artist, SUM(Likes) AS Total_Likes
FROM table6
GROUP BY Artist
ORDER BY SUM(Likes) DESC 
LIMIT 15;''').toPandas()

sqlDF

fig = px.bar(sqlDF, x=sqlDF['Artist'], y=sqlDF['Total_Likes'])
fig.show()


from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score

df


df.columns

Index(['Artist', 'Track', 'Album', 'Album_type', 'Danceability', 'Energy',
       'Key', 'Loudness', 'Speechiness', 'Acousticness', 'Instrumentalness',
       'Liveness', 'Valence', 'Tempo', 'Duration_ms', 'Views', 'Likes',
       'Comments', 'Licensed', 'Stream', 'V/L_Ratio'],
      dtype='object')


# Drop unnecessary columns like track name, artist, album
# Scale the features using StandardScaler
# Split the dataset into training and test sets
X = df.drop(['Artist', 'Track', 'Album', 'Album_type', 'Likes', 'Comments', 'Licensed', 'Stream', 'Views', 'V/L_Ratio'], axis=1)
X = X.values
y = df['Views']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Training the linear regression model
reg = LinearRegression()
reg.fit(X_train, y_train)

# Evaluate the model on the test set
y_pred = reg.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
mae = mean_absolute_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)
print('Mean squared error:', mse)
print('Mean absolute error:', mae)
print('R-squared:', r2)

# Making predictions on new data
new_data = [[0.7, 0.3, 5, -4, 0.2, 0.01, 0.004, 0.09, 0.5, 120, 233347.0], 
            [0.5, 0.25, 7, -5.7, 0.35, 0.06, 0.008, 0.1, 0.8, 78, 363262.0]]
new_preds = reg.predict(new_data)
print('Predictions:', new_preds)

Mean squared error: 6.269089705294543e+16
Mean absolute error: 109784142.56687756
R-squared: 0.020073031150982357
Predictions: [1.44411764e+08 1.24250442e+08]


regRF = RandomForestRegressor(n_estimators=100, random_state=42)
regRF.fit(X_train, y_train)

# Evaluate the model on the test set
y_pred = regRF.predict(X_test)
mse = mean_squared_error(y_test, y_pred)
mae = mean_absolute_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)
print('Mean squared error:', mse)
print('Mean absolute error:', mae)
print('R-squared:', r2)

# Make predictions on new data
new_data = [[0.7, 0.3, 5, -4, 0.2, 0.01, 0.004, 0.09, 0.5, 120, 233347.0], 
            [0.5, 0.25, 7, -5.7, 0.35, 0.06, 0.008, 0.1, 0.8, 78, 363262.0]]
new_preds = regRF.predict(new_data)
print('Predictions:', new_preds)

Mean squared error: 6.5106613912709176e+16
Mean absolute error: 118230420.04959916
R-squared: -0.01768725321672293
Predictions: [3.06437729e+08 3.27065231e+08]

	Danceability	Energy	Key	Loudness	Speechiness	Acousticness	Instrumentalness	Liveness	Valence	Tempo	Duration_ms	Views	Likes	Comments	Stream
count	19549.000000	19549.000000	19549.000000	19549.000000	19549.000000	19549.000000	19549.000000	19549.000000	19549.000000	19549.000000	1.954900e+04	1.954900e+04	1.954900e+04	1.954900e+04	1.954900e+04
mean	0.621059	0.635170	5.294337	-7.633179	0.095392	0.289106	0.055292	0.191226	0.528950	120.605702	2.246281e+05	9.545626e+07	6.700487e+05	2.786371e+04	1.371101e+08
std	0.165489	0.213555	3.579338	4.618839	0.106243	0.285908	0.192519	0.165197	0.245228	29.619340	1.269126e+05	2.775744e+08	1.805054e+06	1.959074e+05	2.463589e+08
min	0.000000	0.000020	0.000000	-46.251000	0.000000	0.000001	0.000000	0.014500	0.000000	0.000000	3.098500e+04	2.600000e+01	0.000000e+00	0.000000e+00	6.574000e+03
25%	0.519000	0.508000	2.000000	-8.772000	0.035700	0.044400	0.000000	0.094000	0.339000	96.990000	1.802400e+05	1.911528e+06	2.238000e+04	5.310000e+02	1.781089e+07
50%	0.639000	0.666000	5.000000	-6.516000	0.050700	0.190000	0.000002	0.125000	0.536000	119.964000	2.132530e+05	1.491440e+07	1.279090e+05	3.343000e+03	4.979139e+07
75%	0.742000	0.797000	8.000000	-4.929000	0.104000	0.470000	0.000433	0.234000	0.725000	139.951000	2.519200e+05	7.152989e+07	5.266400e+05	1.449300e+04	1.390828e+08
max	0.975000	1.000000	11.000000	0.920000	0.964000	0.996000	1.000000	1.000000	0.993000	243.372000	4.676058e+06	8.079649e+09	5.078865e+07	1.608314e+07	3.386520e+09

	Danceability	Energy	Key	Loudness	Speechiness	Acousticness	Instrumentalness	Liveness	Valence	Tempo	Duration_ms	Views	Likes	Comments	Stream
0	0.818	0.705	6.0	-6.679	0.1770	0.008360	0.002330	0.6130	0.7720	138.559	222640.0	693555221.0	6220896.0	169907.0	1.040235e+09
1	0.676	0.703	8.0	-5.815	0.0302	0.086900	0.000687	0.0463	0.8520	92.761	200173.0	72011645.0	1079128.0	31003.0	3.100837e+08
2	0.695	0.923	1.0	-3.930	0.0522	0.042500	0.046900	0.1160	0.5510	108.014	215150.0	8435055.0	282142.0	7399.0	6.306347e+07
3	0.689	0.739	2.0	-5.810	0.0260	0.000015	0.509000	0.0640	0.5780	120.423	233867.0	211754952.0	1788577.0	55229.0	4.346636e+08
4	0.663	0.694	10.0	-8.627	0.1710	0.025300	0.000000	0.0698	0.5250	167.953	340920.0	618480958.0	6197318.0	155930.0	6.172597e+08
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
20713	0.582	0.926	5.0	-6.344	0.0328	0.448000	0.000000	0.0839	0.6580	90.002	94667.0	71678.0	1113.0	0.0	9.227144e+06
20714	0.531	0.936	4.0	-1.786	0.1370	0.028000	0.000000	0.0923	0.6570	174.869	150857.0	164741.0	2019.0	0.0	1.089818e+07
20715	0.443	0.830	4.0	-4.679	0.0647	0.024300	0.000000	0.1540	0.4190	168.388	136842.0	35646.0	329.0	0.0	6.226110e+06
20716	0.417	0.767	9.0	-4.004	0.4190	0.356000	0.018400	0.1080	0.5390	155.378	108387.0	6533.0	88.0	0.0	6.873961e+06
20717	0.498	0.938	6.0	-4.543	0.1070	0.002770	0.911000	0.1360	0.0787	160.067	181500.0	158697.0	2484.0	0.0	5.695584e+06

	Danceability	Energy	Key	Loudness	Speechiness	Acousticness	Instrumentalness	Liveness	Valence	Tempo	Duration_ms	Views	Likes	Comments	Stream
count	16866.000000	16866.000000	16866.000000	16866.000000	16866.000000	16866.000000	16866.000000	16866.000000	16866.000000	16866.000000	1.686600e+04	1.686600e+04	1.686600e+04	1.686600e+04	1.686600e+04
mean	0.619050	0.635350	5.279912	-7.677653	0.094880	0.287854	0.056587	0.191661	0.530527	120.676194	2.226875e+05	8.777338e+07	6.102794e+05	2.543879e+04	1.300308e+08
std	0.165577	0.215155	3.574273	4.637705	0.107337	0.287661	0.193770	0.165636	0.246654	29.685312	9.287362e+04	2.562711e+08	1.644068e+06	1.517489e+05	2.330323e+08
min	0.000000	0.000020	0.000000	-46.251000	0.000000	0.000001	0.000000	0.014500	0.000000	0.000000	3.098500e+04	2.600000e+01	0.000000e+00	0.000000e+00	6.574000e+03
25%	0.515000	0.505000	2.000000	-8.874750	0.035400	0.041500	0.000000	0.094000	0.339000	96.963750	1.808240e+05	1.818648e+06	2.134500e+04	5.100000e+02	1.695603e+07
50%	0.636000	0.666000	5.000000	-6.551500	0.050200	0.186000	0.000003	0.124000	0.538000	119.969000	2.134770e+05	1.381934e+07	1.173160e+05	3.137000e+03	4.813189e+07
75%	0.741000	0.800000	8.000000	-4.946000	0.103000	0.472000	0.000517	0.236000	0.729000	139.982000	2.522248e+05	6.650796e+07	4.807730e+05	1.351250e+04	1.328671e+08
max	0.975000	1.000000	11.000000	0.920000	0.964000	0.996000	1.000000	1.000000	0.993000	243.372000	4.676058e+06	8.079647e+09	5.078863e+07	9.131761e+06	3.386520e+09

	Artist	Track	Album	Album_type	Danceability	Energy	Key	Loudness	Speechiness	Acousticness	Instrumentalness	Liveness	Valence	Tempo	Duration_ms	Views	Likes	Comments	Licensed	Stream
0	The Weeknd	Blinding Lights	After Hours	album	0.514	0.730	1.0	-5.934	0.0598	0.00146	0.000095	0.0897	0.334	171.005	200040.0	6.741645e+08	8817927.0	282589.0	True	3.386520e+09
1	Ed Sheeran	Shape of You	÷ (Deluxe)	album	0.825	0.652	1.0	-3.183	0.0802	0.58100	0.000000	0.0931	0.931	95.977	233713.0	5.908398e+09	31047780.0	1130327.0	True	3.362005e+09
2	Lewis Capaldi	Someone You Loved	Divinely Uninspired To A Hellish Extent	album	0.501	0.405	1.0	-5.679	0.0319	0.75100	0.000000	0.1050	0.446	109.891	182161.0	5.867684e+08	7367091.0	147565.0	True	2.634013e+09
3	Post Malone	rockstar (feat. 21 Savage)	beerbongs & bentleys	album	0.585	0.520	5.0	-6.136	0.0712	0.12400	0.000070	0.1310	0.129	159.801	218147.0	1.060220e+09	12564657.0	366520.0	True	2.594927e+09
4	Swae Lee	Sunflower - Spider-Man: Into the Spider-Verse	Hollywood's Bleeding	album	0.755	0.522	2.0	-4.368	0.0575	0.53300	0.000000	0.0685	0.925	89.960	157560.0	1.977389e+09	13749806.0	331064.0	True	2.538330e+09
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
595	Migos	Walk It Talk It	Culture II	album	0.907	0.633	2.0	-5.145	0.1840	0.08760	0.000003	0.1060	0.395	145.914	276147.0	4.020519e+08	3589336.0	111565.0	True	6.754389e+08
596	Tove Lo	Habits (Stay High)	Queen Of The Clouds	album	0.729	0.650	5.0	-3.539	0.0313	0.07020	0.000067	0.0829	0.347	110.020	209160.0	1.012196e+09	5376201.0	107220.0	True	6.749586e+08
597	A$AP Rocky	F**kin' Problems (feat. Drake, 2 Chainz & Kend...	LONG.LIVE.A$AP (Deluxe Version)	album	0.853	0.693	1.0	-6.870	0.2750	0.02390	0.000000	0.1100	0.662	95.967	233787.0	2.962508e+08	1955320.0	61567.0	True	6.736265e+08
598	Billie Eilish	Bored	Bored	single	0.614	0.318	7.0	-12.695	0.0478	0.89600	0.002390	0.0795	0.112	119.959	180933.0	5.467207e+07	1089600.0	18839.0	True	6.728659e+08
599	Big Sean	I Don't Fuck With You	Dark Sky Paradise	album	0.824	0.733	1.0	-5.474	0.0613	0.03620	0.000000	0.3250	0.395	97.972	284387.0	3.823034e+08	3293569.0	102947.0	True	6.715107e+08

	Artist	Track	Album	Album_type	Danceability	Energy	Key	Loudness	Speechiness	Acousticness	Instrumentalness	Liveness	Valence	Tempo	Duration_ms	Views	Likes	Comments	Licensed	Stream
0	Daddy Yankee	Despacito	VIDA	album	0.655	0.797	2.0	-4.787	0.1530	0.19800	0.000000	0.0670	0.839	177.928	229360.0	8.079647e+09	50788626.0	4252791.0	True	1.506598e+09
1	Ed Sheeran	Shape of You	÷ (Deluxe)	album	0.825	0.652	1.0	-3.183	0.0802	0.58100	0.000000	0.0931	0.931	95.977	233713.0	5.908398e+09	31047780.0	1130327.0	True	3.362005e+09
2	Wiz Khalifa	See You Again (feat. Charlie Puth)	See You Again (feat. Charlie Puth)	single	0.689	0.481	10.0	-7.503	0.0815	0.36900	0.000001	0.0649	0.283	80.025	229526.0	5.773797e+09	40147618.0	2127345.0	True	1.521255e+09
3	CoComelon	Wheels on the Bus	CoComelon Kids Hits, Vol. 1	album	0.941	0.387	9.0	-11.920	0.0427	0.18400	0.000029	0.1570	0.965	125.021	207340.0	4.898831e+09	14396841.0	0.0	True	8.343436e+07
4	Mark Ronson	Uptown Funk (feat. Bruno Mars)	Uptown Special	album	0.856	0.609	0.0	-7.223	0.0824	0.00801	0.000082	0.0344	0.928	114.988	269667.0	4.821016e+09	20067879.0	598916.0	True	1.653820e+09
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
595	Nelly Furtado	Promiscuous - Radio Edit	Promiscuous (Radio Edit)	single	0.786	0.979	10.0	-4.489	0.0440	0.09160	0.000021	0.3490	0.811	114.302	220867.0	5.161938e+08	2735269.0	76338.0	True	1.012045e+07
596	CoComelon	Finger Family	CoComelon Kids Hits, Vol. 2	album	0.816	0.565	9.0	-11.555	0.0360	0.35200	0.000014	0.0768	0.965	119.983	136003.0	5.160842e+08	1714627.0	0.0	True	2.684379e+07
597	Rick Ross	Purple Lamborghini (with Rick Ross)	Purple Lamborghini (with Rick Ross)	single	0.457	0.899	10.0	-2.591	0.1320	0.00190	0.000000	0.8310	0.298	147.268	215510.0	5.160529e+08	4441252.0	147715.0	True	3.736007e+08
598	Prince Royce	Bubalu	Bubalu	compilation	0.800	0.355	6.0	-10.470	0.0895	0.61600	0.000000	0.1180	0.253	145.929	228493.0	5.145548e+08	3010847.0	75208.0	True	3.349868e+08
599	Beyoncé	Love On Top	4	album	0.652	0.749	0.0	-5.248	0.0886	0.08480	0.000000	0.6040	0.651	94.103	267413.0	5.145325e+08	2260106.0	93092.0	True	5.248471e+08

Data Manipulation and Cleaning¶

Checking for redundancy and null values.¶

Exploratory Data Analysis¶

Checking Correlation between features¶

The correlation matrix portrays limited relationship between different characteristics of a soundtrack.¶

We shall further examine the dataset to explore it's integrity.¶

Top Performers¶

Essentially view count signifies YouTube and stream count signifies Spotify¶

Album type classification¶

Top artists on YouTube¶

Top artists on Spotify¶

Top tracks on YouTube¶

Top tracks on Spotify¶

How different metrics influence views or stream?¶

Let's assess how danceability, energy, speechiness, valence and tempo affect view/stream count.¶

Danceability does have a positive correlation with number of expected views. Same is the case with Energy levels.¶

Musicality is celebrated more worldwide which is concluded by 'speechiness' factor of a hit track.¶

Here, speechiness detects the presence of spoken words in a track.¶

Tempo is one essential metric of general composition. However, it isn't the most proper deciding factor for a track's success.¶

As one can see, probability of a hit track is marginally higher when tempo range falls between 70 and 150.¶

Not much can be said about valence. Valence essentially conveys musical positiveness.¶

Although this plot does favor our findings about the tempo range but no clear conclusions can be formed for a track's success.¶

Loudness has the most positive correlation with number of views.¶

Some additional analytics¶

View-like ratio indicates Positive feedback & Audience engagement/loyalty¶

Top Albums¶

Most Liked Artists¶

Prediction modelling using different machine learning algorithms¶

Linear Regression Model¶

The Linear Regression Model doesn't give us a good accurancy with R-squared being close to 0.¶

Random Forest Model¶

Well, a negative R-squared Value always scare me.¶

Conclusion:¶

Clearly, the features of the dataset provide no correlation and any prediction is merely reliable.¶

Hence, our hypothesis is true and the dataset is fundamentally unfit for predictive analysis.¶

	Unnamed: 0	Artist	Url_spotify	Track	Album	Album_type	Uri	Danceability	Energy	Key	...	Url_youtube	Title	Channel	Views	Likes	Comments	Description	Licensed	official_video	Stream
0	0	Gorillaz	https://open.spotify.com/artist/3AA28KZvwAUcZu...	Feel Good Inc.	Demon Days	album	spotify:track:0d28khcov6AiegSCpG5TuT	0.818	0.705	6.0	...	https://www.youtube.com/watch?v=HyHNuVaZJ-k	Gorillaz - Feel Good Inc. (Official Video)	Gorillaz	693555221.0	6220896.0	169907.0	Official HD Video for Gorillaz' fantastic trac...	True	True	1.040235e+09
1	1	Gorillaz	https://open.spotify.com/artist/3AA28KZvwAUcZu...	Rhinestone Eyes	Plastic Beach	album	spotify:track:1foMv2HQwfQ2vntFf9HFeG	0.676	0.703	8.0	...	https://www.youtube.com/watch?v=yYDmaexVHic	Gorillaz - Rhinestone Eyes [Storyboard Film] (...	Gorillaz	72011645.0	1079128.0	31003.0	The official video for Gorillaz - Rhinestone E...	True	True	3.100837e+08
2	2	Gorillaz	https://open.spotify.com/artist/3AA28KZvwAUcZu...	New Gold (feat. Tame Impala and Bootie Brown)	New Gold (feat. Tame Impala and Bootie Brown)	single	spotify:track:64dLd6rVqDLtkXFYrEUHIU	0.695	0.923	1.0	...	https://www.youtube.com/watch?v=qJa-VFwPpYA	Gorillaz - New Gold ft. Tame Impala & Bootie B...	Gorillaz	8435055.0	282142.0	7399.0	Gorillaz - New Gold ft. Tame Impala & Bootie B...	True	True	6.306347e+07
3	3	Gorillaz	https://open.spotify.com/artist/3AA28KZvwAUcZu...	On Melancholy Hill	Plastic Beach	album	spotify:track:0q6LuUqGLUiCPP1cbdwFs3	0.689	0.739	2.0	...	https://www.youtube.com/watch?v=04mfKJWDSzI	Gorillaz - On Melancholy Hill (Official Video)	Gorillaz	211754952.0	1788577.0	55229.0	Follow Gorillaz online:\nhttp://gorillaz.com \...	True	True	4.346636e+08
4	4	Gorillaz	https://open.spotify.com/artist/3AA28KZvwAUcZu...	Clint Eastwood	Gorillaz	album	spotify:track:7yMiX7n9SBvadzox8T5jzT	0.663	0.694	10.0	...	https://www.youtube.com/watch?v=1V_xRb0x9aw	Gorillaz - Clint Eastwood (Official Video)	Gorillaz	618480958.0	6197318.0	155930.0	The official music video for Gorillaz - Clint ...	True	True	6.172597e+08
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
20713	20713	SICK LEGEND	https://open.spotify.com/artist/3EYY5FwDkHEYLw...	JUST DANCE HARDSTYLE	JUST DANCE HARDSTYLE	single	spotify:track:0RtcKQGyI4hr8FgFH1TuYG	0.582	0.926	5.0	...	https://www.youtube.com/watch?v=5SHmKFKlNqI	JUST DANCE HARDSTYLE	SICK LEGEND - Topic	71678.0	1113.0	0.0	Provided to YouTube by Routenote\n\nJUST DANCE...	True	True	9.227144e+06
20714	20714	SICK LEGEND	https://open.spotify.com/artist/3EYY5FwDkHEYLw...	SET FIRE TO THE RAIN HARDSTYLE	SET FIRE TO THE RAIN HARDSTYLE	single	spotify:track:3rHvPA8lUnPBkaLyPOc0VV	0.531	0.936	4.0	...	https://www.youtube.com/watch?v=ocTH6KxllDQ	SET FIRE TO THE RAIN HARDSTYLE	SICK LEGEND - Topic	164741.0	2019.0	0.0	Provided to YouTube by Routenote\n\nSET FIRE T...	True	True	1.089818e+07
20715	20715	SICK LEGEND	https://open.spotify.com/artist/3EYY5FwDkHEYLw...	OUTSIDE HARDSTYLE SPED UP	OUTSIDE HARDSTYLE SPED UP	single	spotify:track:4jk00YxPtPbhvHJE9N4ddv	0.443	0.830	4.0	...	https://www.youtube.com/watch?v=5wFhE-HY0hg	OUTSIDE HARDSTYLE SPED UP	SICK LEGEND - Topic	35646.0	329.0	0.0	Provided to YouTube by Routenote\n\nOUTSIDE HA...	True	True	6.226110e+06
20716	20716	SICK LEGEND	https://open.spotify.com/artist/3EYY5FwDkHEYLw...	ONLY GIRL HARDSTYLE	ONLY GIRL HARDSTYLE	single	spotify:track:5EyErbpsugWliX006eTDex	0.417	0.767	9.0	...	https://www.youtube.com/watch?v=VMFLbFRNCn0	ONLY GIRL HARDSTYLE	SICK LEGEND - Topic	6533.0	88.0	0.0	Provided to YouTube by Routenote\n\nONLY GIRL ...	True	True	6.873961e+06
20717	20717	SICK LEGEND	https://open.spotify.com/artist/3EYY5FwDkHEYLw...	MISS YOU HARDSTYLE	MISS YOU HARDSTYLE	single	spotify:track:6lOn0jz1QpjcWeXo1oMm0k	0.498	0.938	6.0	...	https://www.youtube.com/watch?v=zau0dckCFi0	MISS YOU HARDSTYLE	SICK LEGEND - Topic	158697.0	2484.0	0.0	Provided to YouTube by Routenote\n\nMISS YOU H...	True	True	5.695584e+06

	Artist	Danceability	Energy	Key	Loudness	Speechiness	Acousticness	Instrumentalness	Liveness	Valence	Tempo	Duration_ms	Views	Likes	Comments	Stream
0	Katy Perry	0.655000	0.753000	5.250000	-4.822000	0.053737	0.039957	5.623750e-06	0.245125	0.565875	125.000500	221773.750000	1.552183e+09	7.298340e+06	372232.750000	6.807561e+08
1	Ed Sheeran	0.740375	0.657750	4.375000	-4.809000	0.062950	0.289125	2.311250e-05	0.190438	0.661375	106.736375	216951.875000	1.354188e+09	7.233060e+06	233036.250000	1.251813e+09
2	Dua Lipa	0.773250	0.715500	8.250000	-5.076000	0.076700	0.016010	3.900000e-06	0.099475	0.678000	110.007000	203405.250000	1.232530e+09	8.984291e+06	197210.250000	1.735381e+09
3	CoComelon	0.766857	0.401857	4.428571	-11.320429	0.040029	0.494857	1.900429e-05	0.096957	0.858143	146.948000	144556.428571	1.202930e+09	3.713634e+06	0.000000	3.756832e+07
4	The Weeknd	0.584167	0.637500	1.666667	-6.269333	0.085883	0.085293	1.902500e-05	0.224283	0.380667	142.643500	229499.833333	1.122235e+09	7.641168e+06	235070.666667	1.858146e+09
5	Wiz Khalifa	0.724667	0.651167	7.666667	-5.909333	0.071083	0.207433	1.716667e-07	0.180300	0.541333	136.015000	224813.000000	1.087298e+09	7.409934e+06	393581.666667	4.948412e+08
6	Daddy Yankee	0.772400	0.821200	3.900000	-4.783400	0.069220	0.133920	1.970000e-05	0.138710	0.682200	103.704700	206795.900000	1.087193e+09	6.551817e+06	467212.800000	5.135462e+08
7	Enrique Iglesias	0.671250	0.733125	5.375000	-4.887000	0.060625	0.222550	5.102250e-05	0.114375	0.634500	113.234125	231301.750000	1.040749e+09	3.578378e+06	99921.125000	3.355495e+08
8	DJ Snake	0.629667	0.798500	6.333333	-4.531000	0.103133	0.035372	1.370779e-01	0.192700	0.295167	124.661000	207896.833333	1.031645e+09	6.536074e+06	184021.333333	7.663337e+08
9	Macklemore & Ryan Lewis	0.612000	0.568000	4.000000	-8.555000	0.074300	0.523000	0.000000e+00	0.217000	0.230000	116.247000	346164.000000	1.012206e+09	6.604141e+06	242519.000000	5.662208e+07

	Artist	Danceability	Energy	Key	Loudness	Speechiness	Acousticness	Instrumentalness	Liveness	Valence	Tempo	Duration_ms	Views	Likes	Comments	Stream
0	Drake	0.773000	0.537000	4.000000	-7.410000	0.081300	0.020480	0.000941	0.440500	0.363500	90.568000	186480.000000	8.185059e+08	8.453772e+06	306442.000000	2.312661e+09
1	The Weeknd	0.584167	0.637500	1.666667	-6.269333	0.085883	0.085293	0.000019	0.224283	0.380667	142.643500	229499.833333	1.122235e+09	7.641168e+06	235070.666667	1.858146e+09
2	Dua Lipa	0.773250	0.715500	8.250000	-5.076000	0.076700	0.016010	0.000004	0.099475	0.678000	110.007000	203405.250000	1.232530e+09	8.984291e+06	197210.250000	1.735381e+09
3	Post Malone	0.653571	0.622000	5.714286	-5.355714	0.075086	0.192029	0.000359	0.122471	0.366571	130.840286	200737.428571	4.079678e+08	4.284726e+06	108027.571429	1.513507e+09
4	XXXTENTACION	0.780250	0.524375	5.000000	-8.196125	0.151400	0.400712	0.001613	0.135825	0.430125	124.639125	138198.625000	3.038998e+08	5.270598e+06	373614.125000	1.368585e+09
5	Justin Bieber	0.614000	0.589571	2.428571	-6.922857	0.111143	0.411000	0.000004	0.242914	0.535429	123.849714	181000.000000	8.082079e+08	5.752261e+06	255620.285714	1.313070e+09
6	Shawn Mendes	0.679400	0.622600	6.600000	-7.199600	0.048980	0.221520	0.000029	0.086100	0.605320	121.408200	206256.000000	9.142391e+08	8.889465e+06	283394.600000	1.294543e+09
7	Ed Sheeran	0.740375	0.657750	4.375000	-4.809000	0.062950	0.289125	0.000023	0.190438	0.661375	106.736375	216951.875000	1.354188e+09	7.233060e+06	233036.250000	1.251813e+09
8	Khalid	0.645778	0.573667	3.111111	-7.611111	0.132578	0.309900	0.037364	0.121722	0.343667	111.576778	203433.333333	5.970037e+08	5.162533e+06	110469.333333	1.242641e+09
9	Coldplay	0.472700	0.570400	4.800000	-7.357100	0.030770	0.207006	0.005588	0.177930	0.290600	126.111200	261958.300000	9.997278e+08	6.315790e+06	212437.000000	1.177848e+09